init

FishlifeHH · Feb 6, 2022 · d5f089c · d5f089c
commit d5f089c
Show file tree

Hide file tree

Showing 7 changed files with 25 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -0,0 +1,25 @@
+# OFA
+
+> This is the official repo for the paper: UNIFYING ARCHITECTURES, TASKS, AND MODALITIES THROUGH A SIMPLE SEQUENCE-TO-SEQUENCE LEARNING FRAMEWORK
+
+![Overview](examples/overview.png)
+
+OFA is a unified multimodal pretrained model that unifies modalities (i.e., cross-modality, vision, language) and tasks 
+(e.g., image generation, visual grounding, image captioning, image classification, text generation, etc.) 
+to a simple sequence-tosequence learning framework.
+
+# Examples
+## Image Generation (normal query)
+![t2i_normal](examples/normal_images.png)
+
+## Image Generation (counterfactual query)
+![t2i_counterfactual](examples/counterfactual_images.png)
+
+## Open-Ended VQA
+![open_vqa](examples/open_vqa.png)
+
+## grounded QA
+![grounded_qa](examples/grounded_qa.png)
+
+## Viusal Grounding
+![vg](examples/viusal_grounding.png)
diff --git a/examples/counterfactual_images.png b/examples/counterfactual_images.png
diff --git a/examples/grounded_qa.png b/examples/grounded_qa.png
diff --git a/examples/normal_images.png b/examples/normal_images.png
diff --git a/examples/open_vqa.png b/examples/open_vqa.png
diff --git a/examples/overview.png b/examples/overview.png
diff --git a/examples/viusal_grounding.png b/examples/viusal_grounding.png